{"id":"https://openalex.org/W4411272418","doi":"https://doi.org/10.1109/nlbse66842.2025.00013","title":"Code Comment Classification with Data Augmentation and Transformer-Based Models","display_name":"Code Comment Classification with Data Augmentation and Transformer-Based Models","publication_year":2025,"publication_date":"2025-04-27","ids":{"openalex":"https://openalex.org/W4411272418","doi":"https://doi.org/10.1109/nlbse66842.2025.00013"},"language":"en","primary_location":{"id":"doi:10.1109/nlbse66842.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlbse66842.2025.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Workshop on Natural Language-Based Software Engineering (NLBSE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112504396","display_name":"Mushfiqur Rahman","orcid":null},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mushfiqur Rahman","raw_affiliation_strings":["Bangladesh University of Engineering and Technology,Dhaka,Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083926745","display_name":"Mohammed Latif Siddiq","orcid":"https://orcid.org/0000-0002-7984-3611"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Latif Siddiq","raw_affiliation_strings":["University of Notre Dame,Notre Dame,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Notre Dame,IN,USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6807401776313782},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.467877596616745},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44864895939826965},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.41752079129219055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11048164963722229},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09355205297470093},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05910417437553406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6807401776313782},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.467877596616745},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44864895939826965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41752079129219055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11048164963722229},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09355205297470093},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05910417437553406},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlbse66842.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlbse66842.2025.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Workshop on Natural Language-Based Software Engineering (NLBSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1967995512","https://openalex.org/W2070111972","https://openalex.org/W2607303097","https://openalex.org/W2724503592","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W3098605233","https://openalex.org/W3183010450","https://openalex.org/W3187038508","https://openalex.org/W4385270051","https://openalex.org/W4389681059","https://openalex.org/W4401885626","https://openalex.org/W4402684073","https://openalex.org/W4404989533","https://openalex.org/W4411271391","https://openalex.org/W6755207826","https://openalex.org/W6767552790"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Effective":[0],"classification":[1,107],"of":[2,125],"code":[3,142],"comment":[4],"sentences":[5],"into":[6,61,66],"meaningful":[7],"categories":[8],"is":[9,101,118,143],"critical":[10],"for":[11,23,103],"software":[12],"comprehension":[13],"and":[14,64,77,89,113,133,148],"maintenance.":[15],"In":[16],"this":[17,92],"work,":[18],"we":[19,68],"present":[20],"a":[21,32,45,104],"solution":[22,43],"the":[24,38,58,74,98,122,149],"NLBSE'25":[25],"Code":[26],"Comment":[27],"Classification":[28],"Tool":[29],"Competition,":[30],"achieving":[31],"6.7%":[33],"improvement":[34],"in":[35],"accuracy":[36],"over":[37],"baseline":[39],"STACC":[40],"models.":[41],"Our":[42],"employs":[44],"multi-step":[46],"methodology,":[47],"beginning":[48],"with":[49],"translation-retranslation":[50],"techniques":[51],"to":[52,110,120],"generate":[53],"synthetic":[54],"datasets.":[55],"By":[56],"translating":[57],"original":[59],"dataset":[60],"multiple":[62],"languages":[63],"back":[65],"English,":[67],"introduce":[69],"linguistic":[70],"diversity":[71],"that":[72],"enriches":[73],"training":[75],"data":[76],"improves":[78],"model":[79,100,151],"generalization.":[80],"We":[81],"fine-tuned":[82],"transformer-based":[83],"architectures,":[84],"including":[85],"BERT,":[86],"CodeBERT,":[87],"RoBERTa,":[88],"DistilBERT,":[90],"on":[91],"augmented":[93],"dataset.":[94],"After":[95],"extensive":[96],"evaluation,":[97],"best-performing":[99],"selected":[102],"robust":[105],"multi-label":[106],"framework":[108,117],"tailored":[109],"Java,":[111],"Python,":[112],"Pharo":[114],"databases.":[115],"The":[116,140],"designed":[119],"address":[121],"unique":[123],"challenges":[124],"each":[126],"programming":[127],"language,":[128],"ensuring":[129],"high":[130],"precision,":[131],"recall,":[132],"F1":[134],"scores":[135],"across":[136],"all":[137],"19":[138],"categories.":[139],"source":[141],"publicly":[144],"available":[145],"at":[146,155],"https://github.com/Musfiqur6087/NLBSE-25,":[147],"trained":[150],"can":[152],"be":[153],"accessed":[154],"https://huggingface.comMushfiqurRR.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}